You Only Group Once: Efficient Point-Cloud Processing with Token Representation and Relation Inference Module

03/18/2021
by   Chenfeng Xu, et al.
0

3D point-cloud-based perception is a challenging but crucial computer vision task. A point-cloud consists of a sparse, unstructured, and unordered set of points. To understand a point-cloud, previous point-based methods, such as PointNet++, extract visual features through hierarchically aggregation of local features. However, such methods have several critical limitations: 1) Such methods require several sampling and grouping operations, which slow down the inference speed. 2) Such methods spend an equal amount of computation on each points in a point-cloud, though many of points are redundant. 3) Such methods aggregate local features together through downsampling, which leads to information loss and hurts the perception performance. To overcome these challenges, we propose a novel, simple, and elegant deep learning model called YOGO (You Only Group Once). Compared with previous methods, YOGO only needs to sample and group a point-cloud once, so it is very efficient. Instead of operating on points, YOGO operates on a small number of tokens, each of which summarizes the point features in a sub-region. This allows us to avoid computing on the redundant points and thus boosts efficiency.Moreover, YOGO preserves point-wise features by projecting token features to point features although the computation is performed on tokens. This avoids information loss and can improve point-wise perception performance. We conduct thorough experiments to demonstrate that YOGO achieves at least 3.0x speedup over point-based baselines while delivering competitive classification and segmentation performance on the ModelNet, ShapeNetParts and S3DIS datasets.

READ FULL TEXT
research
07/13/2022

PointNorm: Normalization is All You Need for Point Cloud Analysis

Point cloud analysis is challenging due to the irregularity of the point...
research
05/30/2022

PSNet: Fast Data Structuring for Hierarchical Deep Learning on Point Cloud

In order to retain more feature information of local areas on a point cl...
research
05/02/2022

APP-Net: Auxiliary-point-based Push and Pull Operations for Efficient Point Cloud Classification

Point-cloud-based 3D classification task involves aggregating features f...
research
05/21/2022

Point is a Vector: A Feature Representation in Point Analysis

The irregularity and disorder of point clouds bring many challenges to p...
research
11/26/2021

POEM: 1-bit Point-wise Operations based on Expectation-Maximization for Efficient Point Cloud Processing

Real-time point cloud processing is fundamental for lots of computer vis...
research
08/27/2021

Learning Inner-Group Relations on Point Clouds

The prevalence of relation networks in computer vision is in stark contr...
research
06/21/2023

Fast non-iterative algorithm for 3D point-cloud holography

Recently developed iterative and deep learning-based approaches to compu...

Please sign up or login with your details

Forgot password? Click here to reset